Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1880 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.5668. Min Act: -0.1700
Data Index: 619062 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.3168. Min Act: -0.1700
Data Index: 7215316 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.1918. Min Act: -0.1700
Data Index: 1638883 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.1293. Min Act: -0.1700
Data Index: 1080147 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.1605. Min Act: -0.1700
Data Index: 1202491 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.0980. Min Act: -0.1700
Data Index: 6073966 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.0980. Min Act: -0.1700
Data Index: 1049144 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.0980. Min Act: -0.1700
Data Index: 3149222 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.0668. Min Act: -0.1700
Data Index: 2998522 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.0355. Min Act: -0.1700
Data Index: 2315128 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.0043. Min Act: -0.1700
Data Index: 4817900 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5668. Min Range: -7.5668
Max Act: 7.0043. Min Act: -0.1700
Data Index: 3503604 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5668. Min Range: -7.5668
Max Act: 6.9730. Min Act: -0.1700
Data Index: 8387021 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5668. Min Range: -7.5668
Max Act: 6.9418. Min Act: -0.1700
Data Index: 5452080 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5668. Min Range: -7.5668
Max Act: 6.9730. Min Act: -0.1700
Data Index: 2694205 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5668. Min Range: -7.5668
Max Act: 6.9418. Min Act: -0.1700
Data Index: 3398155 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5668. Min Range: -7.5668
Max Act: 6.9105. Min Act: -0.1700
Data Index: 6175259 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5668. Min Range: -7.5668
Max Act: 6.8793. Min Act: -0.1700
Data Index: 4060960 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5668. Min Range: -7.5668
Max Act: 6.8793. Min Act: -0.1700
Data Index: 3022224 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5668. Min Range: -7.5668
Max Act: 6.8793. Min Act: -0.1700
Data Index: 5439071 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19